A New ANN Approach for Time Series Analysis

Document Type : Article

Authors

1 Department of Industrial Engineering, Meybod University, Iran

2 Industrial Engineering Department, Sharif University of Technology, Iran

3 Industrial Engineering Program, Sabanci University, Turkey

Abstract

Time series analysis and accurate forecasting of energy prices are critical for both policymakers and market participants. In the practical analysis of price time series, the coefficients play vital roles; however, their accurate estimation is a challenging issue as they are affected by external factors. This study proposes a new modelling approach for Artificial Neural Networks (ANNs) models based on fuzzy logic. For this purpose, we reformulated an ANN model as a fuzzy nonlinear regression model to capture the advantages of both fuzzy regression and ANN methodologies. This clear-box model can be applied to not only uncertain, ambiguous, and complex environments, but it is also capable of modelling nonlinear patterns. To illustrate the capability of the proposed approach, we report a case study of liquified natural gas (LNG) prices in Japan’s market (the world’s largest natural gas importer). The results support that the performance of the proposed approach is acceptable; moreover, it can deal with uncertain and complex environments as a clear-box model.

Keywords


References:
[1]           Chen, M.-Y. and Chen, B.-T. “A hybrid fuzzy time series model based on granular computing for stock price forecasting,” Information Sciences, vol. 294, pp. 227–241, Feb. 2015, doi: 10.1016/j.ins.2014.09.038.
[2]           Lu, H. Ma, X. Ma, M. and Zhu, S. “Energy price prediction using data-driven models: A decade review,” Computer Science Review, vol. 39, p. 100356, Feb. 2021, doi: 10.1016/j.cosrev.2020.100356.
[3]           Ryu, S. Noh, J. and Kim, H. “Deep Neural Network Based Demand Side Short Term Load Forecasting,” Energies, vol. 10, no. 1, pp. 1–20, 2016.
[4]           Ziel, F. and Steinert, R. “Probabilistic mid- and long-term electricity price forecasting,” Renewable and Sustainable Energy Reviews, vol. 94, pp. 251–266, Oct. 2018, doi: 10.1016/j.rser.2018.05.038.
[5]           Lago, J. De Ridder, F. and De Schutter, B. “Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms,” Applied Energy, vol. 221, pp. 386–405, Jul. 2018, doi: 10.1016/j.apenergy.2018.02.069.
[6]           Nogales, F.J. and Conejo, A.J. “Electricity price forecasting through transfer function models", Journal of the Operational Research Society, 57(4), 350-356.
[7]           Keynia, F. and Heydari, A. “A new short-term energy price forecasting method based on wavelet neural network,” IJMOR, vol. 14, no. 1, p. 1, 2019, doi: 10.1504/IJMOR.2019.096975.
[8]           Kumar, V. Singh, N. Singh, D.  and Mohanty, S. “Short-Term Electricity Price Forecasting Using Hybrid SARIMA and GJR-GARCH Model,” in Networking Communication and Data Knowledge Engineering, Singapore, 2018, pp. 299–310. doi: 10.1007/978-981-10-4585-1_25.
[9]           Yang, Z. Ce, L. and Lian, L. “Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods,” Applied Energy, vol. 190, pp. 291–305, Mar. 2017, doi: 10.1016/j.apenergy.2016.12.130.
[10]         Lin, L. Jiang, Y. Xiao, H. and Zhou, Z. “Crude oil price forecasting based on a novel hybrid long memory GARCH-M and wavelet analysis model,” Physica A: Statistical Mechanics and its Applications, vol. 543, p. 123532, Apr. 2020, doi: 10.1016/j.physa.2019.123532.
[11]         Zhao, Z. Wang, C. Nokleby, M. and Miller, C. “Improving Short-Term Electricity Price Forecasting Using Day-Ahead LMP with ARIMA Models,” Jan. 2018.
[12]         Trespalacios, A. Cortés, L. and Perote, J. “Uncertainty in electricity markets from a semi-nonparametric approach,” Energy Policy, vol. 137, p. 111091, Feb. 2020, doi: 10.1016/j.enpol.2019.111091.
[13]         Zhang, J. Tan, Z. and Wei, Y. “An adaptive hybrid model for short term electricity price forecasting,” Applied Energy, vol. 258, p. 114087, Jan. 2020, doi: 10.1016/j.apenergy.2019.114087.
[14]         Chen, Y. Zhang, C. He, K. and Zheng, A. “Multi-step-ahead crude oil price forecasting using a hybrid grey wave model,” Physica A: Statistical Mechanics and its Applications, vol. 501, pp. 98–110, Jul. 2018, doi: 10.1016/j.physa.2018.02.061.
[15]         Lei, M. and Feng, Z. “A proposed grey model for short-term electricity price forecasting in competitive power markets,” International Journal of Electrical Power & Energy Systems, vol. 43, no. 1, pp. 531–538, Dec. 2012, doi: 10.1016/j.ijepes.2012.06.001.
[16]         Lei, M. and Feng, Z. A Novel Grey Model to Short-Term Electricity Price Forecasting for NordPool Power Market. 2009, p. 4352. doi: 10.1109/ICSMC.2009.5346948.
[17]         Shrivastava, N. and Panigrahi, B. “A hybrid wavelet-ELM based short term price forecasting for electricity markets,” International Journal of Electrical Power & Energy Systems, vol. 55, pp. 41–50, Feb. 2014, doi: 10.1016/j.ijepes.2013.08.023.
[18]         Su, M. Zhang, Z. Zhu, Y. and Zha, D. “Data-Driven Natural Gas Spot Price Forecasting with Least Squares Regression Boosting Algorithm,” Energies, vol. 12, no. 6, Art. no. 6, Jan. 2019, doi: 10.3390/en12061094.
[19]         Saxena, A. Bansal, R. and Saini, D. Electricity Price Forecasting by Linear Regression and SVM. 2016. doi: 10.1109/ICRAIE.2016.7939509.
[20]         Atef, S. and Eltawil, A. “A Comparative Study Using Deep Learning and Support Vector Regression for Electricity Price Forecasting in Smart Grids,” in 2019 IEEE 6th International Conference on Industrial Engineering and Applications (ICIEA), Apr. 2019, pp. 603–607. doi: 10.1109/IEA.2019.8715213.
[21]         Kuo, P.-H. and Huang, C.-J. “An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks,” Sustainability, vol. 10, p. 1280, Apr. 2018, doi: 10.3390/su10041280.
[22]         Misiorek, A. Trueck, S. and Weron, R. “Point and Interval Forecasting of Spot Electricity Prices: Linear vs. Non-Linear Time Series Models,” Studies in Nonlinear Dynamics & Econometrics, vol. 10, pp. 1362–1362, Feb. 2007, doi: 10.2202/1558-3708.1362.
[23]         Zareipour, H. Bhattacharya, K. and Canizares, C. “Forecasting the hourly Ontario energy price by multivariate adaptive regression splines,” in 2006 IEEE Power Engineering Society General Meeting, Jun. 2006, p. 7 pp.-. doi: 10.1109/PES.2006.1709474.
[24]         Tahir, A. Khan, Z. Javaid, N. Hussain, Z. A. Rasool, and S. Aimal, “Load and Price Forecasting Based on Enhanced Logistic Regression in Smart Grid,” in Advances in Internet, Data and Web Technologies, Cham, 2019, pp. 221–233. doi: 10.1007/978-3-030-12839-5_21.
[25]         Itaba, S. and Mori, H. “A Fuzzy-Preconditioned GRBFN Model for Electricity Price Forecasting,” Procedia Computer Science, vol. 114, pp. 441–448, Jan. 2017, doi: 10.1016/j.procs.2017.09.010.
[26]         Meier, J.H., Schneider, S., Schmidt, I., Schüller, P., Schönfeldt, T. and Wanke, B., 2018, May. "ANN-based electricity price forecasting under special consideration of time series properties". In International Conference on Information and Communication Technologies in Education, Research, and Industrial Applications (pp. 262-275). Springer, Cham.
[27]         Gao, G. Lo, K. and Fan, F. “Comparison of ARIMA and ANN models used in electricity price forecasting for power market,” Energy and Power Engineering, vol. 9, no. 4B, Art. no. 4B, Apr. 2017, doi: 10.4236/epe.2017.94B015.
[28]         Yadav, A. Sahay, A. Yadav, M.  Bhandari, S. Yadav, A. and Sahay, K. “One hour Ahead Short-Term Electricity Price Forecasting Using ANN Algorithms,” in 2018 International Conference and Utility Exhibition on Green Energy for Sustainable Development (ICUE), Oct. 2018, pp. 1–4. doi: 10.23919/ICUE-GESD.2018.8635596.
[29]         Safarinejadian, B. Gharibzadeh, M. and Rakhshan, M. “An optimized model of electricity price forecasting in the electricity market based on fuzzy timeseries,” Systems Science & Control Engineering, vol. 2, no. 1, pp. 677–683, Dec. 2014, doi: 10.1080/21642583.2014.970733.
[30]         Gao, W. Sarlak, V. Parsaei, M. and Ferdosi, M. “Combination of fuzzy based on a meta-heuristic algorithm to predict electricity price in an electricity markets,” Chemical Engineering Research and Design, vol. 131, pp. 333–345, Mar. 2018, doi: 10.1016/j.cherd.2017.09.021.
[31]         Alshejari, A. Kodogiannis, V. and Leonidis, S. “Development of Neurofuzzy Architectures for Electricity Price Forecasting,” Energies, vol. 13, no. 5, Art. no. 5, Jan. 2020, doi: 10.3390/en13051209.
[32]         Azadeh, A. Moghaddam, M. Khakzad, M. and Ebrahimipour, V. “A flexible neural network-fuzzy mathematical programming algorithm for improvement of oil price estimation and forecasting,” Computers & Industrial Engineering, vol. 62, no. 2, pp. 421–430, Mar. 2012, doi: 10.1016/j.cie.2011.06.019.
[33]         Zadeh, L.A., Klir, G.J. and Yuan, B., 1996. "Fuzzy sets, fuzzy logic, and fuzzy systems": selected papers (Vol. 6). World Scientific.
[34]         Ishibuchi, H. Nozaki, K. and Tanaka, H. “Distributed representation of fuzzy rules and its application to pattern classification,” Fuzzy Sets and Systems, vol. 52, no. 1, pp. 21–32, Nov. 1992, doi: 10.1016/0165-0114(92)90032-Y.
[35]         Khashei, M. Rafiei, F. and Bijari, M. “Hybrid Fuzzy Auto-Regressive Integrated Moving Average (FARIMAH) Model for Forecasting the Foreign Exchange Markets,” International Journal of Computational Intelligence Systems, vol. 6, no. 5, pp. 954–968, Sep. 2013, doi: 10.1080/18756891.2013.809937.
[36]         Sahin, Y. and Duman, E. “Detecting credit card fraud by ANN and logistic regression,” in 2011 International Symposium on Innovations in Intelligent Systems and Applications, Jun. 2011, pp. 315–319. doi: 10.1109/INISTA.2011.5946108.
[37]         Zadeh, L. Klir, G. and Yuan, B. Fuzzy Sets, Fuzzy Logic, and Fuzzy Systems: Selected Papers. World Scientific, 1996.
[38]         Souza, P. “Regularized Fuzzy Neural Networks for Pattern Classification Problems,” vol. 13, no. 5, p. 7, 2018.
[39]         Torabi, A. Pashapour Nazari, S. and Neshat, N. “A Novel Approach of Artificial Neural Networks Modeling Based on Fuzzy Regression Approach for Forecasting Purposes: The case of liquid gas price in Japan’s market,” Advances in Industrial Engineering, vol. 47, no. 1, pp. 15–24, Mar. 2013, doi: 10.22059/jieng.2013.35507.
[40]         Atil, A. Lahiani, A. and Nguyen, D. “Asymmetric and nonlinear pass-through of crude oil prices to gasoline and natural gas prices,” Energy Policy, vol. 65, pp. 567–573, Feb. 2014, doi: 10.1016/j.enpol.2013.09.064.
[41]         Hailemariam, A. and Smyth, R. “What drives volatility in natural gas prices?,” Energy Economics, vol. 80, pp. 731–742, May 2019, doi: 10.1016/j.eneco.2019.02.011.
[42]         Jianglin, H. “Comparing the Natural Gas Pipeline Pricing between Europe and America and the Revelation to China,” Energy Procedia, vol. 5, pp. 659–663, Jan. 2011, doi: 10.1016/j.egypro.2011.03.116.
[43]         Maxwell, D. and Zhu, Z. “Natural gas prices, LNG transport costs, and the dynamics of LNG imports,” Energy Economics, vol. 33, no. 2, pp. 217–226, Mar. 2011, doi: 10.1016/j.eneco.2010.06.012.
[44]   Nick, S. and Thoenes, S. “What drives natural gas prices? — A structural VAR approach,” Energy Economics, vol. 45, pp. 517–527, Sep. 2014, doi: 10.1016/j.eneco.2014.08.010